Assessing performance of ZCTA-level and Census Tract-level social and environmental risk factors in a model predicting hospital events

Predictive analytics are used in primary care to efficiently direct health care resources to high-risk patients to prevent unnecessary health care utilization and improve health. Social determinants of health (SDOH) are important features in these models, but they are poorly measured in administrative claims data. Area-level SDOH can be proxies for unavailable individual-level indicators, but the extent to which the granularity of risk factors impacts predictive models is unclear. We examined whether increasing the granularity of area-based SDOH features from ZIP code tabulation area (ZCTA) to Census Tract strengthened an existing clinical prediction model for avoidable hospitalizations (AH events) in Maryland Medicare fee-for-service beneficiaries. We created a person-month dataset for 465,749 beneficiaries (59.4% female; 69.8% White; 22.7% Black) with 144 features indexing medical history and demographics using Medicare claims (September 2018 through July 2021). Claims data were linked with 37 SDOH features associated with AH events from 11 publicly-available sources (e.g., American Community Survey) based on the beneficiaries' ZCTA and Census Tract of residence. Individual AH risk was estimated using six discrete time survival models with different combinations of demographic, condition/utilization, and SDOH features. Each model used stepwise variable selection to retain only meaningful predictors. We compared model fit, predictive performance, and interpretation across models. Results showed that increasing the granularity of area-based risk factors did not dramatically improve model fit or predictive performance. However, it did affect model interpretation by altering which SDOH features were retained during variable selection. Further, the inclusion of SDOH at either granularity level meaningfully reduced the risk that was attributed to demographic predictors (e.g., race, dual-eligibility for Medicaid). Differences in interpretation are critical given that this model is used by primary care staff to inform the allocation of care management resources, including those available to address drivers of health beyond the bounds of traditional health care.

Health Information Technology Adoption in the Emergency Department

OBJECTIVE

To describe the trend in health information technology (IT) systems adoption in hospital emergency departments (EDs) and its effect on ED efficiency and resource use.

DATA SOURCES

2007-2010 National Hospital Ambulatory Medical Care Survey - ED Component.

STUDY DESIGN

We assessed changes in the percent of visits to EDs with health IT capability and the estimated effect on waiting time to see a provider, visit length, and resource use.

PRINCIPAL FINDINGS

The percent of ED visits that took place in an ED with at least a basic health IT or an advanced IT system increased from 25.2 and 3.1 percent in 2007 to 69.1 and 30.6 percent in 2010, respectively (p < .05). Controlling for ED fixed effects, waiting times were reduced by 6.0 minutes in advanced IT-equipped EDs (p < .05), and the number of tests ordered increased by 9 percent (p < .01). In models using a 1-year lag, advanced systems also showed an increase in the number of medications and images ordered per visit.

CONCLUSIONS

Almost a third of visits now occur in EDs with advanced IT capability. While advanced IT adoption may decrease wait times, resource use during ED visits may also increase depending on how long the system has been in place. We were not able to determine if these changes indicated more appropriate care.